M3: A Multi-View Fusion and Multi-Decoding Network for Multi-Document Reading Comprehension

Liang Wen, Houfeng Wang, Yingwei Luo, Xiaolin Wang


Abstract
Multi-document reading comprehension task requires collecting evidences from different documents for answering questions. Previous research works either use the extractive modeling method to naively integrate the scores from different documents on the encoder side or use the generative modeling method to collect the clues from different documents on the decoder side individually. However, any single modeling method cannot make full of the advantages of both. In this work, we propose a novel method that tries to employ a multi-view fusion and multi-decoding mechanism to achieve it. For one thing, our approach leverages question-centered fusion mechanism and cross-attention mechanism to gather fine-grained fusion of evidence clues from different documents in the encoder and decoder concurrently. For another, our method simultaneously employs both the extractive decoding approach and the generative decoding method to effectively guide the training process. Compared with existing methods, our method can perform both extractive decoding and generative decoding independently and optionally. Our experiments on two mainstream multi-document reading comprehension datasets (Natural Questions and TriviaQA) demonstrate that our method can provide consistent improvements over previous state-of-the-art methods.
Anthology ID:
2022.emnlp-main.94
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1450–1461
Language:
URL:
https://aclanthology.org/2022.emnlp-main.94
DOI:
10.18653/v1/2022.emnlp-main.94
Bibkey:
Cite (ACL):
Liang Wen, Houfeng Wang, Yingwei Luo, and Xiaolin Wang. 2022. M3: A Multi-View Fusion and Multi-Decoding Network for Multi-Document Reading Comprehension. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1450–1461, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
M3: A Multi-View Fusion and Multi-Decoding Network for Multi-Document Reading Comprehension (Wen et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.94.pdf